Over the past decade, the healthcare industry has shifted to electronic health records (EHRs) with the goal of improving patient care. The learning curve has been steep, but as EHR processes have become normalized, we’ve reached the next stage to better integrate EHR data with other datasets.
It is common for people to wear devices that monitor personal health data, such as heartbeat, blood sugar, fitness, sleep, and even mental health. Video chats and calls have also increased in prominence as the population gets more comfortable with these devices and the technology becomes more accessible. With such an abundant amount of data being collected, integrating these rich datasets generated through telemedicine with EHR systems is a technical challenge for healthcare information technologists. But, ultimately, this integration can lead to a better patient experience and predictive care with greater accuracy in diagnoses.
Useful Data Types to Capture through Telemedicine
Most people focus on telemedicine as a way of delivering care to or in remote areas, or reducing the patient’s burden of travel to a distant specialist. A less commonly described benefit of telemedicine is that the data gleaned from the video and audio could result in better diagnoses.
It is quite common during a telemedicine patient encounter for the doctor to be looking down at a computer or tablet, entering a patient’s responses. It can be easy to miss information based on facial expressions or body language.
One way to avoid this issue could be to analyze the data captured through telemedicine sessions using the robust tools offered by healthcare data analytics. Having the ability to use automated machine learning applications to review the session during or after the patient has left could improve patient care by
- providing the doctor with a record of the answers, potentially leading to easier and more accurate data entry;
- analytically comparing the patient’s mode of communication from past appointments to understand change, evaluating changes in audio or body movement; and
- analyzing micro-expressions in the patient to get a better sense of state of mind incorporating the findings within the patients EHR.
What is a Micro-Expression?
Micro-expressions are “brief and subtle facial movements” that reveal “an emotion a person is trying to conceal.” Scientists assert that these micro-expressions are universal across cultures and are becoming more easily recognizable through the use of technology. The publically available app, Affectiva, illustrates how this works. When the user makes a facial expression, the app scores the expression along common emotions. These scores could assist doctors in better diagnoses regardless of language or mental health challenges that make it difficult for the patient to communicate. Even large retail stores, such as Walmart, have recognized the value of micro-expressions as they consider a new approach to improving customer service by installing video systems which monitor customers' facial expressions as they move through the store.
Using telemedicine technology is not only useful in identifying emotions or comparing datasets. Identifying post-traumatic stress disorder in both military and civilian populations has become a growing need, and there have been advances in diagnosing whether patients are suffering PTSD through analyzing their speech. Recording telemedicine sessions provides baseline video and audio for comparison. This can assist a doctor who is evaluating the progression of degenerative diseases, such as Alzheimer’s or ALS, as well as evaluating whether someone has had a micro-stroke.
Planning for Telemedicine in Today’s Healthcare Technology Investments
Our society’s technology is constantly changing, requiring extra planning needs when it comes to incorporating these capabilities into our everyday lives. For example, when planning a new building, it is important to design for the technologies of the future. For those architecting healthcare technologies, the use of telemedicine is growing quickly. Approximately 83 percent of healthcare executives surveyed by the American Telemedicine Association said they would be likely or very likely to invest in telehealth in 2017.
The key barrier to telemedicine adoption, according to this survey, was inadequate coverage of telemedicine services by insurance. That barrier could be reduced through legislation under consideration to incentivize testing more telehealth services in Medicare healthcare delivery.
This could result in reimbursement to healthcare providers who incorporate telemedicine in their delivery.
Direct compensation for telemedicine services is not the only reason to invest in these technologies. For an example of success in telemedicine, healthcare providers can look to Veterans Affairs, which reduced hospital admissions by 35 percent in some cases while providing healthcare to veterans often living remotely.
The same technologies used in telemedicine could assist those in other industries. LMI's healthcare analytics team has the knowledge and experience to work with your healthcare information technology teams to build robust EHR systems.
I will be discussing the topic of integrating predictive analytics and telemedicine with the EHR at the 5th International Conference on Medical Informatics & Telemedicine, August 31, 2017 in Prague, Czech Republic.
 Shen X, Wu Q, Fu X. “Effects of the Duration of Expressions on the Recognition of Microexpressions.” J Zhejiang Univ Sci B. 2012; 13(3): 221–230.
 Ekman P, Friesen WV, O’Sullivan, et al. “Universals and Cultural Differences in Facial Expressions of Emotion.” J Pers Soc Psychol. 1987; 53(4):712:717.
 D. Vergyri, B. Knoth, E. Shriberg, V. Mitra, M. McLaren, L. Ferrer, P. Garcia, C. Marmar, "Speech-Based Assessment of PTSD in a Military Population Using Diverse Feature Classes," in Proc. Interspeech 2015, pp. 3,729–3,733.
 American Telemedicine Association, Executive Leadership Survey, March 2017.
 To require the Center for Medicare and Medicaid Innovation to test the effect of including telehealth services in Medicare health care delivery reform models. S. 787. 115th Cong. (2017).